skill-creator

Generate SKILL.md scaffolds and run iterative evaluation loops for AI skills.

229|5|Updated Apr 9, 2026
One-click install
npx skills add https://github.com/760485464/qyclaw --skill skill-creator-760485464
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/760485464/qyclaw/tree/main/skills-builtin/skill-creator
Command: npx skills add https://github.com/760485464/qyclaw --skill skill-creator-760485464

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pyyaml, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill helps teams create, test, and iterate AI skills by providing structured guidance and automation for drafting, evaluating, and refining SKILL.md entries, running evals, and tracking improvements to trigger accuracy.

Core Features & Use Cases

  • Generates a complete SKILL.md scaffold from a given idea, including frontmatter and inline instructions.
  • Orchestrates iterative evaluation loops: run eval prompts, collect results, analyze, and rewrite the skill description based on feedback.
  • Packages finalized skills into distributable artifacts and provides guidance for benchmarking and description optimization.

Quick Start

Provide a complete SKILL.md scaffold and run a basic evaluation loop to bootstrap a new skill.

Frequently Asked Questions about skill-creator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a SKILL.md scaffold from a basic idea?

To create a SKILL.md scaffold, provide your initial idea and the tool generates a complete structure featuring frontmatter and inline instructions. This scaffolding process establishes the foundational document needed to define your skill's purpose and scope.

How does an iterative evaluation loop work for refining AI skills?

An iterative evaluation loop runs eval prompts, collects results, analyzes the output, and rewrites the skill description based on feedback. This automated workflow continuously refines trigger accuracy and improves the skill's semantic search indexing.

What is the best way to package finalized skills into distributable artifacts?

The best way to package finalized skills is to use the skill-creator's packaging automation, which bundles the SKILL.md and related resources into distributable artifacts. This process provides guidance for benchmarking and optimizing descriptions for deployment.

Do I need pyyaml installed to generate and evaluate SKILL.md files?

Yes, you need pyyaml installed because it is a required dependency for the skill-creator. This library handles YAML parsing, which is essential for processing the frontmatter in your SKILL.md files during the generation and evaluation workflows.

Why should I distill skill triggers into indexing-friendly language?

You should distill skill triggers into indexing-friendly language to ensure semantic search engines can accurately match user queries with your skill's capabilities. Emphasizing user-facing practical usage scenarios over implementation specifics improves trigger accuracy.